concept high dimension in category deep learning
appears as: higher dimensions, high dimensions

This is an excerpt from Manning's book Math and Architectures of Deep Learning.
The geometric view holds in higher dimensions too. In general, a n-dimensional input vector
is mapped to a m-dimensional output vector (usually m < n) in such a way that the problem becomes much simpler in the output space. An example with 3D feature space is shown in Figure 1.3.
This holds true in general, and for higher dimensions too. This is the mental picture to have with respect to independent versus non-independent point distributions.